INDEX

Explanations

phrases related to government intelligence activities and policies

oai_token-act-pair · gpt-3.5-turbo

terms related to foreign intelligence and policy

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TPS

-0.78

Cooldown

-0.75

amaz

-0.74

FORMATION

-0.73

raper

-0.70

CHAT

-0.68

esville

-0.67

Roll

-0.66

GM

-0.66

ikan

-0.64

POSITIVE LOGITS

 Confederation

0.75

 correspondent

0.73

 Affairs

0.73

 espionage

0.72

bia

0.69

 subt

0.69

 Diplom

0.68

 abroad

0.68

uador

0.68

 Lavrov

0.67

Activations Density 0.051%

phrases related to government intelligence activities and policies

terms related to foreign intelligence and policy

No Comments

No Known Activations